{"id":"https://openalex.org/W4404781551","doi":"https://doi.org/10.18653/v1/2024.wmt-1.42","title":"The Bangla/Bengali Seed Dataset Submission to the WMT24 Open Language Data Initiative Shared Task","display_name":"The Bangla/Bengali Seed Dataset Submission to the WMT24 Open Language Data Initiative Shared Task","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404781551","doi":"https://doi.org/10.18653/v1/2024.wmt-1.42"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.wmt-1.42","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.wmt-1.42","pdf_url":"https://aclanthology.org/2024.wmt-1.42.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.wmt-1.42.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031780725","display_name":"Firoz Ahmed","orcid":"https://orcid.org/0000-0002-4781-4736"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Firoz Ahmed","raw_affiliation_strings":["University of Florida University of Florida University of Florida"],"affiliations":[{"raw_affiliation_string":"University of Florida University of Florida University of Florida","institution_ids":["https://openalex.org/I33213144","https://openalex.org/I2800717037","https://openalex.org/I94062374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054644891","display_name":"Nitin Venkateswaran","orcid":null},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin Venkateswaran","raw_affiliation_strings":["University of Florida University of Florida University of Florida"],"affiliations":[{"raw_affiliation_string":"University of Florida University of Florida University of Florida","institution_ids":["https://openalex.org/I33213144","https://openalex.org/I2800717037","https://openalex.org/I94062374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065106608","display_name":"Sarah Moeller","orcid":"https://orcid.org/0000-0003-3612-2811"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Moeller","raw_affiliation_strings":["University of Florida University of Florida University of Florida"],"affiliations":[{"raw_affiliation_string":"University of Florida University of Florida University of Florida","institution_ids":["https://openalex.org/I33213144","https://openalex.org/I2800717037","https://openalex.org/I94062374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031780725"],"corresponding_institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I33213144","https://openalex.org/I94062374"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19491389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.9946345090866089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853706479072571},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.693905770778656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6001309156417847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448940992355347},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32321465015411377},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05432024598121643}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9946345090866089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853706479072571},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.693905770778656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6001309156417847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448940992355347},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32321465015411377},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05432024598121643},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.wmt-1.42","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.wmt-1.42","pdf_url":"https://aclanthology.org/2024.wmt-1.42.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Conference on Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.wmt-1.42","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.wmt-1.42","pdf_url":"https://aclanthology.org/2024.wmt-1.42.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404781551.pdf","grobid_xml":"https://content.openalex.org/works/W4404781551.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W2028401451","https://openalex.org/W2769530083","https://openalex.org/W3161006337","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"contribute":[1],"a":[2,27],"seed":[3],"dataset":[4,25,32,70,94],"for":[5,61,99],"the":[6,12,21,24,48,56,75,87,100],"Bangla/Bengali":[7,101],"language":[8],"as":[9],"part":[10],"of":[11,23,39,50,89],"WMT24":[13],"Open":[14],"Language":[15],"Data":[16],"Initiative":[17],"shared":[18],"task.We":[19],"validate":[20],"quality":[22,88],"against":[26],"mined":[28],"and":[29,34,83,103],"automatically":[30],"aligned":[31],"(NLLBv1)":[33],"two":[35],"other":[36,76],"existing":[37],"datasets":[38,58,77],"crowdsourced":[40],"manual":[41],"translations.The":[42],"validation":[43],"is":[44],"performed":[45],"by":[46],"investigating":[47],"performance":[49],"state-of-the-art":[51],"translation":[52,65,80,98],"models":[53,66,72],"fine-tuned":[54,67],"on":[55,68,74],"different":[57],"after":[59],"controlling":[60],"training":[62],"set":[63],"size.Machine":[64],"our":[69,90,93],"outperform":[71],"tuned":[73],"in":[78],"both":[79],"directions":[81],"(English-Bangla":[82],"Bangla-English).These":[84],"results":[85],"confirm":[86],"dataset.We":[91],"hope":[92],"will":[95],"support":[96],"machine":[97],"community":[102],"related":[104],"low-resource":[105],"languages.":[106]},"counts_by_year":[],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}
